open-powerlifting-GAM

setup

rr rm(list = ls()) library(tidyverse) library(ggplot2) library(car) library(scam)

download data

rr if (file.exists(-2020-06-20/openpowerlifting-2020-06-20.csv)){ data.working <- read.csv(-2020-06-20/openpowerlifting-2020-06-20.csv) } else { download.file(://github.com/sstangl/openpowerlifting-static/raw/gh-pages/openpowerlifting-latest.zip, -latest.zip) unzip(-latest.zip)

data.working <- read.csv(-2020-06-20/openpowerlifting-2020-06-20.csv) }

filter data

rr data.working <- data.working %>% filter(Event == , Equipment == , !is.na(Age), !is.na(BodyweightKg), !is.na(TotalKg), ParentFederation == )

creating features

rr data.working <- data.working %>% mutate(AgeBucket = as.factor(case_when( Age <= 19 ~ , Age >= 20 & Age <= 23 ~ , Age >= 24 & Age <= 35 ~ , Age >= 36 ~ , TRUE ~ ))) %>% mutate(Federation = as.factor(Federation)) # Adding weightclass data.working\(WeightclassKg_Calc <- \error\ data.working[data.working\)Sex == ,_Calc] <- data.working %>% filter(Sex == ) %>% transmute(WeightclassKg_Calc = as.character(cut(BodyweightKg, c(0,53,59,66,74,83,93,105,120,9999)))) data.working[data.working\(Sex == \F\,\WeightclassKg_Calc\] <- data.working %>% filter(Sex == \F\) %>% transmute(WeightclassKg_Calc = as.character(cut(BodyweightKg, c(0,43,47,52,57,63,72,84,9999)))) data.working\)WeightclassKg_Calc <- as.factor(data.working$WeightclassKg_Calc)

rr weightclasses <- unique(data.working$WeightclassKg_Calc)

intra-weightclass scam

monotone increasing concave –> bs = “micv”

rr for (each in weightclasses){

Warning messages:
1: In readChar(file, size, TRUE) : truncating string with embedded nuls
2: In readChar(file, size, TRUE) : truncating string with embedded nuls
3: In readChar(file, size, TRUE) : truncating string with embedded nuls
4: In readChar(file, size, TRUE) : truncating string with embedded nuls
5: In readChar(file, size, TRUE) : truncating string with embedded nuls

rr

df_tmp <- data.working %>% filter(WeightclassKg_Calc == each) %>% select(TotalKg, BodyweightKg)

scam_tmp <- scam(data = df_tmp, TotalKg ~ s(BodyweightKg, bs = ))

df_tmp$scam_predict <- predict(scam_tmp)

print(ggplot(df_tmp) + geom_point(aes(x = BodyweightKg, y = TotalKg)) + geom_line(aes(x = BodyweightKg, y = scam_predict), color = , size = 2) + ggtitle(paste(each, : Raw with GAM)))

data.working[data.working\(WeightclassKg_Calc == each, \TotalKg_scam\] <- data.working[data.working\)WeightclassKg_Calc == each, ] / df_tmp$scam_predict

print(ggplot(data.working %>% filter(WeightclassKg_Calc == each)) + geom_point(aes(x = BodyweightKg, y = TotalKg_scam)) + ggtitle(paste(each, : Transformed))) }

rr ggplot(data.working %>% filter(Sex == )) + geom_point(aes(x = BodyweightKg, y = TotalKg_scam))

rr ggplot(data.working %>% filter(Sex == )) + geom_point(aes(x = BodyweightKg, y = TotalKg_scam))

box-cox

rr box_cox_df <- matrix(ncol = 2, nrow = length(unique(data.working\(WeightclassKg_Calc))) # dataframe of optimal lambdas for (x in 1:length(weightclasses)){ tmp <- data.working %>% filter(WeightclassKg_Calc == weightclasses[x]) box_cox_df[x,1] <- as.character(weightclasses[x]) box_cox_df[x,2] <- powerTransform(tmp\)TotalKg_scam)\(lambda } box_cox_df <- as.data.frame(box_cox_df) colnames(box_cox_df) <- c(\WeightclassKg\, \lambda\) box_cox_df\)WeightclassKg <- as.character(box_cox_df\(WeightclassKg) box_cox_df\)lambda <- as.numeric(box_cox_df\(lambda) box_cox_df ``` ```r # applying box-cox w/ said optimal lambda data.working\)SCORE <- 0 for (each in weightclasses){ x = data.working[data.working\(WeightclassKg_Calc == each,\TotalKg_scam\] data.working[data.working\)WeightclassKg_Calc == each,] <- bcPower(x,box_cox_df[box_cox_df\(WeightclassKg == each,\lambda\]) } # divide by mean for (each in weightclasses){ data.working[data.working\)WeightclassKg_Calc == each,] <- scale(data.working[data.working$WeightclassKg_Calc == each,]) }

visualize box cox results

rr # individual weight classes for (each in weightclasses){ tmp <- data.working %>% filter(WeightclassKg_Calc == each) %>% select(SCORE)

gg <- ggplot(tmp) + geom_density(aes(x = SCORE)) + ggtitle(each)

print(gg) }

rr # male / female for (each in c(, )){ print(ggplot(data.working %>% filter(Sex == each)) + geom_point((aes(x = BodyweightKg, y = SCORE))) + ggtitle(paste(=,each))) }

Top Men & Women

rr data.working %>% arrange(desc(SCORE)) %>% filter(Sex == ) %>% filter(row_number() <11) r data.working %>% arrange(desc(SCORE)) %>% filter(Sex == ) %>% filter(row_number() <11)

rr NA

Validation: Deciles

# test out other scores...